[PATCH 8/8] lguest: the documentation, example launcher

[Rusty Russell <rusty@rustcorp.com.au>]

A brief document describing how to use lguest.  Because lguest doesn't
have an ABI we also include an example launcher in the Documentation
directory.

Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
---
 Documentation/lguest/Makefile   |   20 
 Documentation/lguest/lguest.c   |  982 +++++++++++++++++++++++++++++++++++++++
 Documentation/lguest/lguest.txt |  125 ++++
 3 files changed, 1127 insertions(+)

===================================================================
--- /dev/null
+++ b/Documentation/lguest/Makefile
@@ -0,0 +1,20 @@
+# This creates the demonstration utility "lguest" which runs a Linux guest.
+
+# We rely on CONFIG_PAGE_OFFSET to know where to put lguest binary.
+include ../../.config
+LGUEST_GUEST_TOP := ($(CONFIG_PAGE_OFFSET) - 0x08000000)
+
+CFLAGS:=-Wall -Wmissing-declarations -Wmissing-prototypes -O3 \
+	-static -DLGUEST_GUEST_TOP="$(LGUEST_GUEST_TOP)" -Wl,-T,lguest.lds
+LDLIBS:=-lz
+
+all: lguest.lds lguest
+
+# The linker script on x86 is so complex the only way of creating one
+# which will link our binary in the right place is to mangle the
+# default one.
+lguest.lds:
+	$(LD) --verbose | awk '/^==========/ { PRINT=1; next; } /SIZEOF_HEADERS/ { gsub(/0x[0-9A-F]*/, "$(LGUEST_GUEST_TOP)") } { if (PRINT) print $$0; }' > $@
+
+clean:
+	rm -f lguest.lds lguest
===================================================================
--- /dev/null
+++ b/Documentation/lguest/lguest.c
@@ -0,0 +1,982 @@
+/* Simple program to layout "physical" memory for new lguest guest.
+ * Linked high to avoid likely physical memory.  */
+#define _LARGEFILE64_SOURCE
+#define _GNU_SOURCE
+#include <stdio.h>
+#include <string.h>
+#include <unistd.h>
+#include <err.h>
+#include <stdint.h>
+#include <stdlib.h>
+#include <elf.h>
+#include <sys/mman.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <sys/wait.h>
+#include <fcntl.h>
+#include <stdbool.h>
+#include <errno.h>
+#include <signal.h>
+#include <ctype.h>
+#include <sys/socket.h>
+#include <sys/ioctl.h>
+#include <sys/time.h>
+#include <time.h>
+#include <netinet/in.h>
+#include <net/if.h>
+#include <linux/sockios.h>
+#include <linux/if_tun.h>
+#include <sys/uio.h>
+#include <termios.h>
+#include <getopt.h>
+#include <zlib.h>
+typedef uint32_t u32;
+typedef uint16_t u16;
+typedef uint8_t u8;
+#include "../../include/linux/lguest_launcher.h"
+
+#define PAGE_PRESENT 0x7 	/* Present, RW, Execute */
+#define NET_PEERNUM 1
+#define BRIDGE_PFX "bridge:"
+
+static bool verbose;
+#define verbose(args...) \
+	do { if (verbose) printf(args); } while(0)
+
+struct device_list
+{
+	fd_set infds;
+	int max_infd;
+
+	struct device *dev;
+	struct device **lastdev;
+};
+
+struct device
+{
+	struct device *next;
+	struct lguest_device_desc *desc;
+	void *mem;
+
+	/* Watch this fd if handle_input non-NULL. */
+	int fd;
+	bool (*handle_input)(int fd, struct device *me);
+
+	/* Watch DMA to this key if handle_input non-NULL. */
+	unsigned long watch_key;
+	u32 (*handle_output)(int fd, const struct iovec *iov,
+			     unsigned int num, struct device *me);
+
+	/* Device-specific data. */
+	void *priv;
+};
+
+static int open_or_die(const char *name, int flags)
+{
+	int fd = open(name, flags);
+	if (fd < 0)
+		err(1, "Failed to open %s", name);
+	return fd;
+}
+
+static void *map_zeroed_pages(unsigned long addr, unsigned int num)
+{
+	static int fd = -1;
+
+	if (fd == -1)
+		fd = open_or_die("/dev/zero", O_RDONLY);
+
+	if (mmap((void *)addr, getpagesize() * num,
+		 PROT_READ|PROT_WRITE|PROT_EXEC, MAP_FIXED|MAP_PRIVATE, fd, 0)
+	    != (void *)addr)
+		err(1, "Mmaping %u pages of /dev/zero @%p", num, (void *)addr);
+	return (void *)addr;
+}
+
+/* Returns the entry point */
+static unsigned long map_elf(int elf_fd, const Elf32_Ehdr *ehdr,
+			     unsigned long *page_offset)
+{
+	void *addr;
+	Elf32_Phdr phdr[ehdr->e_phnum];
+	unsigned int i;
+
+	/* Sanity checks. */
+	if (ehdr->e_type != ET_EXEC
+	    || ehdr->e_machine != EM_386
+	    || ehdr->e_phentsize != sizeof(Elf32_Phdr)
+	    || ehdr->e_phnum < 1 || ehdr->e_phnum > 65536U/sizeof(Elf32_Phdr))
+		errx(1, "Malformed elf header");
+
+	if (lseek(elf_fd, ehdr->e_phoff, SEEK_SET) < 0)
+		err(1, "Seeking to program headers");
+	if (read(elf_fd, phdr, sizeof(phdr)) != sizeof(phdr))
+		err(1, "Reading program headers");
+
+	*page_offset = 0;
+	/* We map the loadable segments at virtual addresses corresponding
+	 * to their physical addresses (our virtual == guest physical). */
+	for (i = 0; i < ehdr->e_phnum; i++) {
+		if (phdr[i].p_type != PT_LOAD)
+			continue;
+
+		verbose("Section %i: size %i addr %p\n",
+			i, phdr[i].p_memsz, (void *)phdr[i].p_paddr);
+
+		/* We expect linear address space. */
+		if (!*page_offset)
+			*page_offset = phdr[i].p_vaddr - phdr[i].p_paddr;
+		else if (*page_offset != phdr[i].p_vaddr - phdr[i].p_paddr)
+			errx(1, "Page offset of section %i different", i);
+
+		/* We map everything private, writable. */
+		addr = mmap((void *)phdr[i].p_paddr,
+			    phdr[i].p_filesz,
+			    PROT_READ|PROT_WRITE|PROT_EXEC,
+			    MAP_FIXED|MAP_PRIVATE,
+			    elf_fd, phdr[i].p_offset);
+		if (addr != (void *)phdr[i].p_paddr)
+			err(1, "Mmaping vmlinux seg %i gave %p not %p",
+			    i, addr, (void *)phdr[i].p_paddr);
+	}
+
+	/* Entry is physical address: convert to virtual */
+	return ehdr->e_entry + *page_offset;
+}
+
+/* This is amazingly reliable. */
+static unsigned long intuit_page_offset(unsigned char *img, unsigned long len)
+{
+	unsigned int i, possibilities[256] = { 0 };
+
+	for (i = 0; i + 4 < len; i++) {
+		/* mov 0xXXXXXXXX,%eax */
+		if (img[i] == 0xA1 && ++possibilities[img[i+4]] > 3)
+			return (unsigned long)img[i+4] << 24;
+	}
+	errx(1, "could not determine page offset");
+}
+
+static unsigned long unpack_bzimage(int fd, unsigned long *page_offset)
+{
+	gzFile f;
+	int ret, len = 0;
+	void *img = (void *)0x100000;
+
+	f = gzdopen(fd, "rb");
+	if (gzdirect(f))
+		errx(1, "did not find correct gzip header");
+	while ((ret = gzread(f, img + len, 65536)) > 0)
+		len += ret;
+	if (ret < 0)
+		err(1, "reading image from bzImage");
+
+	verbose("Unpacked size %i addr %p\n", len, img);
+	*page_offset = intuit_page_offset(img, len);
+
+	/* Entry is physical address: convert to virtual */
+	return (unsigned long)img + *page_offset;
+}
+
+static unsigned long load_bzimage(int fd, unsigned long *page_offset)
+{
+	unsigned char c;
+	int state = 0;
+
+	/* Ugly brute force search for gzip header. */
+	while (read(fd, &c, 1) == 1) {
+		switch (state) {
+		case 0:
+			if (c == 0x1F)
+				state++;
+			break;
+		case 1:
+			if (c == 0x8B)
+				state++;
+			else
+				state = 0;
+			break;
+		case 2 ... 8:
+			state++;
+			break;
+		case 9:
+			lseek(fd, -10, SEEK_CUR);
+			if (c != 0x03) /* Compressed under UNIX. */
+				state = -1;
+			else
+				return unpack_bzimage(fd, page_offset);
+		}
+	}
+	errx(1, "Could not find kernel in bzImage");
+}
+
+static unsigned long load_kernel(int fd, unsigned long *page_offset)
+{
+	Elf32_Ehdr hdr;
+
+	if (read(fd, &hdr, sizeof(hdr)) != sizeof(hdr))
+		err(1, "Reading kernel");
+
+	if (memcmp(hdr.e_ident, ELFMAG, SELFMAG) == 0)
+		return map_elf(fd, &hdr, page_offset);
+
+	return load_bzimage(fd, page_offset);
+}
+
+/* initrd gets loaded at top of memory: return length. */
+static unsigned long load_initrd(const char *name, unsigned long mem)
+{
+	int ifd;
+	struct stat st;
+	void *iaddr;
+
+	ifd = open_or_die(name, O_RDONLY);
+	if (fstat(ifd, &st) < 0)
+		err(1, "fstat() on initrd '%s'", name);
+
+	iaddr = mmap((void *)mem - st.st_size, st.st_size,
+		     PROT_READ|PROT_EXEC|PROT_WRITE,
+		     MAP_FIXED|MAP_PRIVATE, ifd, 0);
+	if (iaddr != (void *)mem - st.st_size)
+		err(1, "Mmaping initrd '%s' returned %p not %p",
+		    name, iaddr, (void *)mem - st.st_size);
+	close(ifd);
+	verbose("mapped initrd %s size=%lu @ %p\n", name, st.st_size, iaddr);
+	return st.st_size;
+}
+
+static inline unsigned long page_align(unsigned long addr)
+{
+	return ((addr + getpagesize()-1) & ~(getpagesize()-1));
+}
+
+static unsigned long setup_pagetables(unsigned long mem,
+				      unsigned long initrd_size,
+				      unsigned long page_offset)
+{
+	u32 *pgdir, *linear;
+	unsigned int mapped_pages, i, linear_pages;
+	unsigned int ptes_per_page = getpagesize()/sizeof(u32);
+
+	/* If we can map all of memory above page_offset, we do so. */
+	if (mem > -page_offset)
+		mapped_pages = mem/getpagesize();
+	else
+		mapped_pages = -page_offset/getpagesize();
+
+	/* Each linear PTE page can map ptes_per_page pages. */
+	linear_pages = (mapped_pages + ptes_per_page-1)/ptes_per_page;
+
+	/* We lay out top-level then linear mapping immediately below initrd */
+	pgdir = (void *)mem - initrd_size - getpagesize();
+	linear = (void *)pgdir - linear_pages*getpagesize();
+
+	for (i = 0; i < mapped_pages; i++)
+		linear[i] = ((i * getpagesize()) | PAGE_PRESENT);
+
+	/* Now set up pgd so that this memory is at page_offset */
+	for (i = 0; i < mapped_pages; i += ptes_per_page) {
+		pgdir[(i + page_offset/getpagesize())/ptes_per_page]
+			= (((u32)linear + i*sizeof(u32)) | PAGE_PRESENT);
+	}
+
+	verbose("Linear mapping of %u pages in %u pte pages at %p\n",
+		mapped_pages, linear_pages, linear);
+
+	return (unsigned long)pgdir;
+}
+
+static void concat(char *dst, char *args[])
+{
+	unsigned int i, len = 0;
+
+	for (i = 0; args[i]; i++) {
+		strcpy(dst+len, args[i]);
+		strcat(dst+len, " ");
+		len += strlen(args[i]) + 1;
+	}
+	/* In case it's empty. */
+	dst[len] = '\0';
+}
+
+static int tell_kernel(u32 pgdir, u32 start, u32 page_offset)
+{
+	u32 args[] = { LHREQ_INITIALIZE,
+		       LGUEST_GUEST_TOP/getpagesize(), /* Just below us */
+		       pgdir, start, page_offset };
+	int fd;
+
+	fd = open_or_die("/dev/lguest", O_RDWR);
+	if (write(fd, args, sizeof(args)) < 0)
+		err(1, "Writing to /dev/lguest");
+	return fd;
+}
+
+static void set_fd(int fd, struct device_list *devices)
+{
+	FD_SET(fd, &devices->infds);
+	if (fd > devices->max_infd)
+		devices->max_infd = fd;
+}
+
+/* We send lguest_add signals while input is pending: avoids races. */
+static void wake_parent(int pipefd, struct device_list *devices)
+{
+	nice(19);
+
+	set_fd(pipefd, devices);
+
+	for (;;) {
+		fd_set rfds = devices->infds;
+
+		select(devices->max_infd+1, &rfds, NULL, NULL, NULL);
+		if (FD_ISSET(pipefd, &rfds)) {
+			int ignorefd;
+			if (read(pipefd, &ignorefd, sizeof(ignorefd)) == 0)
+				exit(0);
+			FD_CLR(ignorefd, &devices->infds);
+		}
+		kill(getppid(), SIGUSR1);
+	}
+}
+
+/* We don't want signal to kill us, just jerk us out of kernel. */
+static void wakeup(int signo)
+{
+}
+
+static int setup_waker(struct device_list *device_list)
+{
+	int pipefd[2], child;
+	struct sigaction act;
+
+	act.sa_handler = wakeup;
+	sigemptyset(&act.sa_mask);
+	act.sa_flags = 0;
+	sigaction(SIGUSR1, &act, NULL);
+
+	pipe(pipefd);
+	child = fork();
+	if (child == -1)
+		err(1, "forking");
+
+	if (child == 0) {
+		close(pipefd[1]);
+		wake_parent(pipefd[0], device_list);
+	}
+	close(pipefd[0]);
+
+	return pipefd[1];
+}
+
+static void *_check_pointer(unsigned long addr, unsigned int size,
+			    unsigned int line)
+{
+	if (addr >= LGUEST_GUEST_TOP || addr + size >= LGUEST_GUEST_TOP)
+		errx(1, "%s:%i: Invalid address %li", __FILE__, line, addr);
+	return (void *)addr;
+}
+#define check_pointer(addr,size) _check_pointer(addr, size, __LINE__)
+
+/* Returns pointer to dma->used_len */
+static u32 *dma2iov(unsigned long dma, struct iovec iov[], unsigned *num)
+{
+	unsigned int i;
+	struct lguest_dma *udma;
+
+	udma = check_pointer(dma, sizeof(*udma));
+	for (i = 0; i < LGUEST_MAX_DMA_SECTIONS; i++) {
+		if (!udma->len[i])
+			break;
+
+		iov[i].iov_base = check_pointer(udma->addr[i], udma->len[i]);
+		iov[i].iov_len = udma->len[i];
+	}
+	*num = i;
+	return &udma->used_len;
+}
+
+static u32 *get_dma_buffer(int fd, void *key,
+			   struct iovec iov[], unsigned int *num, u32 *irq)
+{
+	u32 buf[] = { LHREQ_GETDMA, (u32)key };
+	unsigned long udma;
+	u32 *res;
+
+	udma = write(fd, buf, sizeof(buf));
+	if (udma == (unsigned long)-1)
+		return NULL;
+
+	/* Kernel stashes irq in ->used_len. */
+	res = dma2iov(udma, iov, num);
+	*irq = *res;
+	return res;
+}
+
+static void trigger_irq(int fd, u32 irq)
+{
+	u32 buf[] = { LHREQ_IRQ, irq };
+	if (write(fd, buf, sizeof(buf)) != 0)
+		err(1, "Triggering irq %i", irq);
+}
+
+static void discard_iovec(struct iovec *iov, unsigned int *num)
+{
+	static char discard_buf[1024];
+	*num = 1;
+	iov->iov_base = discard_buf;
+	iov->iov_len = sizeof(discard_buf);
+}
+
+static struct termios orig_term;
+static void restore_term(void)
+{
+	tcsetattr(STDIN_FILENO, TCSANOW, &orig_term);
+}
+
+struct console_abort
+{
+	int count;
+	struct timeval start;
+};
+
+/* We DMA input to buffer bound at start of console page. */
+static bool handle_console_input(int fd, struct device *dev)
+{
+	u32 irq = 0, *lenp;
+	int len;
+	unsigned int num;
+	struct iovec iov[LGUEST_MAX_DMA_SECTIONS];
+	struct console_abort *abort = dev->priv;
+
+	lenp = get_dma_buffer(fd, dev->mem, iov, &num, &irq);
+	if (!lenp) {
+		warn("console: no dma buffer!");
+		discard_iovec(iov, &num);
+	}
+
+	len = readv(dev->fd, iov, num);
+	if (len <= 0) {
+		warnx("Failed to get console input, ignoring console.");
+		len = 0;
+	}
+
+	if (lenp) {
+		*lenp = len;
+		trigger_irq(fd, irq);
+	}
+
+	/* Three ^C within one second?  Exit. */
+	if (len == 1 && ((char *)iov[0].iov_base)[0] == 3) {
+		if (!abort->count++)
+			gettimeofday(&abort->start, NULL);
+		else if (abort->count == 3) {
+			struct timeval now;
+			gettimeofday(&now, NULL);
+			if (now.tv_sec <= abort->start.tv_sec+1)
+				exit(2);
+			abort->count = 0;
+		}
+	} else
+		abort->count = 0;
+
+	if (!len) {
+		restore_term();
+		return false;
+	}
+	return true;
+}
+
+static u32 handle_console_output(int fd, const struct iovec *iov,
+				 unsigned num, struct device*dev)
+{
+	return writev(STDOUT_FILENO, iov, num);
+}
+
+static u32 handle_tun_output(int fd, const struct iovec *iov,
+			     unsigned num, struct device *dev)
+{
+	/* Now we've seen output, we should warn if we can't get buffers. */
+	*(bool *)dev->priv = true;
+	return writev(dev->fd, iov, num);
+}
+
+static unsigned long peer_offset(unsigned int peernum)
+{
+	return 4 * peernum;
+}
+
+static bool handle_tun_input(int fd, struct device *dev)
+{
+	u32 irq = 0, *lenp;
+	int len;
+	unsigned num;
+	struct iovec iov[LGUEST_MAX_DMA_SECTIONS];
+
+	lenp = get_dma_buffer(fd, dev->mem+peer_offset(NET_PEERNUM), iov, &num,
+			      &irq);
+	if (!lenp) {
+		if (*(bool *)dev->priv)
+			warn("network: no dma buffer!");
+		discard_iovec(iov, &num);
+	}
+
+	len = readv(dev->fd, iov, num);
+	if (len <= 0)
+		err(1, "reading network");
+	if (lenp) {
+		*lenp = len;
+		trigger_irq(fd, irq);
+	}
+	verbose("tun input packet len %i [%02x %02x] (%s)\n", len,
+		((u8 *)iov[0].iov_base)[0], ((u8 *)iov[0].iov_base)[1],
+		lenp ? "sent" : "discarded");
+	return true;
+}
+
+static u32 handle_block_output(int fd, const struct iovec *iov,
+			       unsigned num, struct device *dev)
+{
+	struct lguest_block_page *p = dev->mem;
+	u32 irq, *lenp;
+	unsigned int len, reply_num;
+	struct iovec reply[LGUEST_MAX_DMA_SECTIONS];
+	off64_t device_len, off = (off64_t)p->sector * 512;
+
+	device_len = *(off64_t *)dev->priv;
+
+	if (off >= device_len)
+		err(1, "Bad offset %llu vs %llu", off, device_len);
+	if (lseek64(dev->fd, off, SEEK_SET) != off)
+		err(1, "Bad seek to sector %i", p->sector);
+
+	verbose("Block: %s at offset %llu\n", p->type ? "WRITE" : "READ", off);
+
+	lenp = get_dma_buffer(fd, dev->mem, reply, &reply_num, &irq);
+	if (!lenp)
+		err(1, "Block request didn't give us a dma buffer");
+
+	if (p->type) {
+		len = writev(dev->fd, iov, num);
+		if (off + len > device_len) {
+			ftruncate(dev->fd, device_len);
+			errx(1, "Write past end %llu+%u", off, len);
+		}
+		*lenp = 0;
+	} else {
+		len = readv(dev->fd, reply, reply_num);
+		*lenp = len;
+	}
+
+	p->result = 1 + (p->bytes != len);
+	trigger_irq(fd, irq);
+	return 0;
+}
+
+static void handle_output(int fd, unsigned long dma, unsigned long key,
+			  struct device_list *devices)
+{
+	struct device *i;
+	u32 *lenp;
+	struct iovec iov[LGUEST_MAX_DMA_SECTIONS];
+	unsigned num = 0;
+
+	lenp = dma2iov(dma, iov, &num);
+	for (i = devices->dev; i; i = i->next) {
+		if (i->handle_output && key == i->watch_key) {
+			*lenp = i->handle_output(fd, iov, num, i);
+			return;
+		}
+	}
+	warnx("Pending dma %p, key %p", (void *)dma, (void *)key);
+}
+
+static void handle_input(int fd, int childfd, struct device_list *devices)
+{
+	struct timeval poll = { .tv_sec = 0, .tv_usec = 0 };
+
+	for (;;) {
+		struct device *i;
+		fd_set fds = devices->infds;
+
+		if (select(devices->max_infd+1, &fds, NULL, NULL, &poll) == 0)
+			break;
+
+		for (i = devices->dev; i; i = i->next) {
+			if (i->handle_input && FD_ISSET(i->fd, &fds)) {
+				if (!i->handle_input(fd, i)) {
+					FD_CLR(i->fd, &devices->infds);
+					/* Tell child to ignore it too... */
+					write(childfd, &i->fd, sizeof(i->fd));
+				}
+			}
+		}
+	}
+}
+
+static struct lguest_device_desc *new_dev_desc(u16 type, u16 features,
+					       u16 num_pages)
+{
+	static unsigned long top = LGUEST_GUEST_TOP;
+	struct lguest_device_desc *desc;
+
+	desc = malloc(sizeof(*desc));
+	desc->type = type;
+	desc->num_pages = num_pages;
+	desc->features = features;
+	desc->status = 0;
+	if (num_pages) {
+		top -= num_pages*getpagesize();
+		map_zeroed_pages(top, num_pages);
+		desc->pfn = top / getpagesize();
+	} else
+		desc->pfn = 0;
+	return desc;
+}
+
+static struct device *new_device(struct device_list *devices,
+				 u16 type, u16 num_pages, u16 features,
+				 int fd,
+				 bool (*handle_input)(int, struct device *),
+				 unsigned long watch_off,
+				 u32 (*handle_output)(int,
+						      const struct iovec *,
+						      unsigned,
+						      struct device *))
+{
+	struct device *dev = malloc(sizeof(*dev));
+
+	/* Append to device list. */
+	*devices->lastdev = dev;
+	dev->next = NULL;
+	devices->lastdev = &dev->next;
+
+	dev->fd = fd;
+	if (handle_input)
+		set_fd(dev->fd, devices);
+	dev->desc = new_dev_desc(type, features, num_pages);
+	dev->mem = (void *)(dev->desc->pfn * getpagesize());
+	dev->handle_input = handle_input;
+	dev->watch_key = (unsigned long)dev->mem + watch_off;
+	dev->handle_output = handle_output;
+	return dev;
+}
+
+static void setup_console(struct device_list *devices)
+{
+	struct device *dev;
+
+	if (tcgetattr(STDIN_FILENO, &orig_term) == 0) {
+		struct termios term = orig_term;
+		term.c_lflag &= ~(ISIG|ICANON|ECHO);
+		tcsetattr(STDIN_FILENO, TCSANOW, &term);
+		atexit(restore_term);
+	}
+
+	/* We don't currently require a page for the console. */
+	dev = new_device(devices, LGUEST_DEVICE_T_CONSOLE, 0, 0,
+			 STDIN_FILENO, handle_console_input,
+			 LGUEST_CONSOLE_DMA_KEY, handle_console_output);
+	dev->priv = malloc(sizeof(struct console_abort));
+	((struct console_abort *)dev->priv)->count = 0;
+	verbose("device %p: console\n",
+		(void *)(dev->desc->pfn * getpagesize()));
+}
+
+static void setup_block_file(const char *filename, struct device_list *devices)
+{
+	int fd;
+	struct device *dev;
+	off64_t *device_len;
+	struct lguest_block_page *p;
+
+	fd = open_or_die(filename, O_RDWR|O_LARGEFILE|O_DIRECT);
+	dev = new_device(devices, LGUEST_DEVICE_T_BLOCK, 1,
+			 LGUEST_DEVICE_F_RANDOMNESS,
+			 fd, NULL, 0, handle_block_output);
+	device_len = dev->priv = malloc(sizeof(*device_len));
+	*device_len = lseek64(fd, 0, SEEK_END);
+	p = dev->mem;
+
+	p->num_sectors = *device_len/512;
+	verbose("device %p: block %i sectors\n",
+		(void *)(dev->desc->pfn * getpagesize()), p->num_sectors);
+}
+
+/* We use fnctl locks to reserve network slots (autocleanup!) */
+static unsigned int find_slot(int netfd, const char *filename)
+{
+	struct flock fl;
+
+	fl.l_type = F_WRLCK;
+	fl.l_whence = SEEK_SET;
+	fl.l_len = 1;
+	for (fl.l_start = 0;
+	     fl.l_start < getpagesize()/sizeof(struct lguest_net);
+	     fl.l_start++) {
+		if (fcntl(netfd, F_SETLK, &fl) == 0)
+			return fl.l_start;
+	}
+	errx(1, "No free slots in network file %s", filename);
+}
+
+static void setup_net_file(const char *filename,
+			   struct device_list *devices)
+{
+	int netfd;
+	struct device *dev;
+
+	netfd = open(filename, O_RDWR, 0);
+	if (netfd < 0) {
+		if (errno == ENOENT) {
+			netfd = open(filename, O_RDWR|O_CREAT, 0600);
+			if (netfd >= 0) {
+				char page[getpagesize()];
+				memset(page, 0, sizeof(page));
+				write(netfd, page, sizeof(page));
+			}
+		}
+		if (netfd < 0)
+			err(1, "cannot open net file '%s'", filename);
+	}
+
+	dev = new_device(devices, LGUEST_DEVICE_T_NET, 1,
+			 find_slot(netfd, filename)|LGUEST_NET_F_NOCSUM,
+			 -1, NULL, 0, NULL);
+
+	/* We overwrite the /dev/zero mapping with the actual file. */
+	if (mmap(dev->mem, getpagesize(), PROT_READ|PROT_WRITE,
+			 MAP_FIXED|MAP_SHARED, netfd, 0) != dev->mem)
+			err(1, "could not mmap '%s'", filename);
+	verbose("device %p: shared net %s, peer %i\n",
+		(void *)(dev->desc->pfn * getpagesize()), filename,
+		dev->desc->features & ~LGUEST_NET_F_NOCSUM);
+}
+
+static u32 str2ip(const char *ipaddr)
+{
+	unsigned int byte[4];
+
+	sscanf(ipaddr, "%u.%u.%u.%u", &byte[0], &byte[1], &byte[2], &byte[3]);
+	return (byte[0] << 24) | (byte[1] << 16) | (byte[2] << 8) | byte[3];
+}
+
+/* adapted from libbridge */
+static void add_to_bridge(int fd, const char *if_name, const char *br_name)
+{
+	int ifidx;
+	struct ifreq ifr;
+
+	if (!*br_name)
+		errx(1, "must specify bridge name");
+
+	ifidx = if_nametoindex(if_name);
+	if (!ifidx)
+		errx(1, "interface %s does not exist!", if_name);
+
+	strncpy(ifr.ifr_name, br_name, IFNAMSIZ);
+	ifr.ifr_ifindex = ifidx;
+	if (ioctl(fd, SIOCBRADDIF, &ifr) < 0)
+		err(1, "can't add %s to bridge %s", if_name, br_name);
+}
+
+static void configure_device(int fd, const char *devname, u32 ipaddr,
+			     unsigned char hwaddr[6])
+{
+	struct ifreq ifr;
+	struct sockaddr_in *sin = (struct sockaddr_in *)&ifr.ifr_addr;
+
+	memset(&ifr, 0, sizeof(ifr));
+	strcpy(ifr.ifr_name, devname);
+	sin->sin_family = AF_INET;
+	sin->sin_addr.s_addr = htonl(ipaddr);
+	if (ioctl(fd, SIOCSIFADDR, &ifr) != 0)
+		err(1, "Setting %s interface address", devname);
+	ifr.ifr_flags = IFF_UP;
+	if (ioctl(fd, SIOCSIFFLAGS, &ifr) != 0)
+		err(1, "Bringing interface %s up", devname);
+
+	if (ioctl(fd, SIOCGIFHWADDR, &ifr) != 0)
+		err(1, "getting hw address for %s", devname);
+
+	memcpy(hwaddr, ifr.ifr_hwaddr.sa_data, 6);
+}
+
+static void setup_tun_net(const char *arg, struct device_list *devices)
+{
+	struct device *dev;
+	struct ifreq ifr;
+	int netfd, ipfd;
+	u32 ip;
+	const char *br_name = NULL;
+
+	netfd = open_or_die("/dev/net/tun", O_RDWR);
+	memset(&ifr, 0, sizeof(ifr));
+	ifr.ifr_flags = IFF_TAP | IFF_NO_PI;
+	strcpy(ifr.ifr_name, "tap%d");
+	if (ioctl(netfd, TUNSETIFF, &ifr) != 0)
+		err(1, "configuring /dev/net/tun");
+
+	/* You will be peer 1: we should create enough jitter to randomize */
+	dev = new_device(devices, LGUEST_DEVICE_T_NET, 1,
+			 NET_PEERNUM|LGUEST_DEVICE_F_RANDOMNESS, netfd,
+			 handle_tun_input, peer_offset(0), handle_tun_output);
+	dev->priv = malloc(sizeof(bool));
+	*(bool *)dev->priv = false;
+
+	ipfd = socket(PF_INET, SOCK_DGRAM, IPPROTO_IP);
+	if (ipfd < 0)
+		err(1, "opening IP socket");
+
+	if (!strncmp(BRIDGE_PFX, arg, strlen(BRIDGE_PFX))) {
+		ip = INADDR_ANY;
+		br_name = arg + strlen(BRIDGE_PFX);
+		add_to_bridge(ipfd, ifr.ifr_name, br_name);
+	} else
+		ip = str2ip(arg);
+
+	/* We are peer 0, ie. first slot. */
+	configure_device(ipfd, ifr.ifr_name, ip, dev->mem);
+	close(ipfd);
+
+	verbose("device %p: tun net %u.%u.%u.%u\n",
+		(void *)(dev->desc->pfn * getpagesize()),
+		(u8)(ip>>24), (u8)(ip>>16), (u8)(ip>>8), (u8)ip);
+	if (br_name)
+		verbose("attached to bridge: %s\n", br_name);
+}
+
+/* Now we know how much memory we have, we copy in device descriptors */
+static void map_device_descriptors(struct device_list *devs, unsigned long mem)
+{
+	struct device *i;
+	unsigned int num;
+	struct lguest_device_desc *descs;
+
+	/* Device descriptor array sits just above top of normal memory */
+	descs = map_zeroed_pages(mem, 1);
+
+	for (i = devs->dev, num = 0; i; i = i->next, num++) {
+		if (num == LGUEST_MAX_DEVICES)
+			errx(1, "too many devices");
+		verbose("Device %i: %s\n", num,
+			i->desc->type == LGUEST_DEVICE_T_NET ? "net"
+			: i->desc->type == LGUEST_DEVICE_T_CONSOLE ? "console"
+			: i->desc->type == LGUEST_DEVICE_T_BLOCK ? "block"
+			: "unknown");
+		descs[num] = *i->desc;
+		free(i->desc);
+		i->desc = &descs[num];
+	}
+}
+
+static void __attribute__((noreturn))
+run_guest(int lguest_fd, int waker_fd, struct device_list *device_list)
+{
+	sigset_t sigset;
+
+	sigemptyset(&sigset);
+	sigaddset(&sigset, SIGUSR1);
+	for (;;) {
+		unsigned long arr[2];
+		int readval;
+
+		sigprocmask(SIG_UNBLOCK, &sigset, NULL);
+		readval = read(lguest_fd, arr, sizeof(arr));
+		sigprocmask(SIG_BLOCK, &sigset, NULL);
+
+		if (readval == sizeof(arr))
+			handle_output(lguest_fd, arr[0], arr[1], device_list);
+		else if (errno == ENOENT) {
+			char reason[1024] = { 0 };
+			read(lguest_fd, reason, sizeof(reason)-1);
+			errx(1, "%s", reason);
+		} else if (errno != EINTR)
+			err(1, "Running guest failed");
+		handle_input(lguest_fd, waker_fd, device_list);
+	}
+}
+
+static struct option opts[] = {
+	{ "verbose", 0, NULL, 'v' },
+	{ "sharenet", 1, NULL, 's' },
+	{ "tunnet", 1, NULL, 't' },
+	{ "block", 1, NULL, 'b' },
+	{ "initrd", 1, NULL, 'i' },
+};
+static void usage(void)
+{
+	errx(1, "Usage: lguest [--verbose] "
+	     "[--sharenet=<filename>|--tunnet=(<ipaddr>|bridge:<bridgename>)\n"
+	     "|--block=<filename>|--initrd=<filename>]...\n"
+	     "<mem-in-mb> vmlinux [args...]");
+}
+
+int main(int argc, char *argv[])
+{
+	unsigned long mem, pgdir, start, page_offset;
+	int c, lguest_fd, waker_fd;
+	struct device_list device_list;
+	struct lguest_boot_info *boot = (void *)0;
+	const char *initrd_name = NULL;
+
+	device_list.max_infd = -1;
+	device_list.dev = NULL;
+	device_list.lastdev = &device_list.dev;
+	FD_ZERO(&device_list.infds);
+
+	while ((c = getopt_long(argc, argv, "v", opts, NULL)) != EOF) {
+		switch (c) {
+		case 'v':
+			verbose = true;
+			break;
+		case 's':
+			setup_net_file(optarg, &device_list);
+			break;
+		case 't':
+			setup_tun_net(optarg, &device_list);
+			break;
+		case 'b':
+			setup_block_file(optarg, &device_list);
+			break;
+		case 'i':
+			initrd_name = optarg;
+			break;
+		default:
+			warnx("Unknown argument %s", argv[optind]);
+			usage();
+		}
+	}
+	if (optind + 2 > argc)
+		usage();
+
+	/* We need a console device */
+	setup_console(&device_list);
+
+	/* First we map /dev/zero over all of guest-physical memory. */
+	mem = atoi(argv[optind]) * 1024 * 1024;
+	map_zeroed_pages(0, mem / getpagesize());
+
+	/* Now we load the kernel */
+	start = load_kernel(open_or_die(argv[optind+1], O_RDONLY),
+			    &page_offset);
+
+	/* Write the device descriptors into memory. */
+	map_device_descriptors(&device_list, mem);
+
+	/* Map the initrd image if requested */
+	if (initrd_name)
+		boot->initrd_size = load_initrd(initrd_name, mem);
+
+	/* Set up the initial linar pagetables. */
+	pgdir = setup_pagetables(mem, boot->initrd_size, page_offset);
+
+	/* Give the guest the boot information it needs. */
+	concat(boot->cmdline, argv+optind+2);
+	boot->max_pfn = mem/getpagesize();
+
+	lguest_fd = tell_kernel(pgdir, start, page_offset);
+	waker_fd = setup_waker(&device_list);
+
+	run_guest(lguest_fd, waker_fd, &device_list);
+}
===================================================================
--- /dev/null
+++ b/Documentation/lguest/lguest.txt
@@ -0,0 +1,125 @@
+Rusty's Remarkably Unreliable Guide to Lguest
+	- or, A Young Coder's Illustrated Hypervisor
+http://lguest.ozlabs.org
+
+Lguest is designed to be a minimal hypervisor for the Linux kernel, for
+Linux developers and users to experiment with virtualization with the
+minimum of complexity.  Nonetheless, it should have sufficient
+features to make it useful for specific tasks, and, of course, you are
+encouraged to fork and enhance it.
+
+Features:
+
+- Kernel module which runs in a normal kernel.
+- Simple I/O model for communication.
+- Simple program to create new guests.
+- Logo contains cute puppies: http://lguest.ozlabs.org
+
+Developer features:
+
+- Fun to hack on.
+- No ABI: being tied to a specific kernel anyway, you can change anything.
+- Many opportunities for improvement or feature implementation.
+
+Running Lguest:
+
+- You will need to configure your kernel with the following options:
+
+  CONFIG_HIGHMEM64G=n ("High Memory Support" "64GB")[1]
+  CONFIG_TUN=y/m ("Universal TUN/TAP device driver support")
+  CONFIG_EXPERIMENTAL=y ("Prompt for development and/or incomplete code/drivers")
+  CONFIG_PARAVIRT=y ("Paravirtualization support (EXPERIMENTAL)")
+  CONFIG_LGUEST=y/m ("Linux hypervisor example code")
+
+  and I recommend:
+  CONFIG_HZ=100 ("Timer frequency")[2]
+
+- A tool called "lguest" is available in this directory: type "make"
+  to build it.
+
+- Create or find a root disk image.  There are several useful ones
+  around, such as the xm-test tiny root image at
+	  http://xm-test.xensource.com/ramdisks/initrd-1.1-i386.img
+
+  For more serious work, I usually use a distribution ISO image and
+  install it under qemu, then make multiple copies:
+
+	  dd if=/dev/zero of=rootfile bs=1M count=2048
+	  qemu -cdrom image.iso -hda rootfile -net user -net nic -boot d
+
+- "modprobe lg" if you built it as a module.
+
+- Run an lguest as root:
+
+      Documentation/lguest/lguest 64m vmlinux --tunnet=192.168.19.1 --block=rootfile root=/dev/lgba
+
+   Explanation:
+    64m: the amount of memory to use.
+
+    vmlinux: the kernel image found in the top of your build directory.  You
+       can also use a standard bzImage.
+
+    --tunnet=192.168.19.1: configures a "tap" device for networking with this
+       IP address.
+
+    --block=rootfile: a file or block device which becomes /dev/lgba
+       inside the guest.
+
+    root=/dev/lgba: this (and anything else on the command line) are
+       kernel boot parameters.
+
+- Configuring networking.  I usually have the host masquerade, using
+  "iptables -t nat -o eth0 -j MASQUERADE" and "echo 1 >
+  /proc/sys/net/ipv4/ip_forward".  In this example, I would configure
+  eth0 inside the guest at 192.168.19.2.
+
+  Another method is to bridge the tap device to an external interface
+  using --tunnet=bridge:<bridgename>, and perhaps run dhcp on the guest
+  to obtain an IP address.  The bridge needs to be configured first:
+  this option simply adds the tap interface to it.
+
+  A simple example on my system:
+
+    ifconfig eth0 0.0.0.0
+    brctl addbr lg0
+    ifconfig lg0 up
+    brctl addif lg0 eth0
+    dhclient lg0
+
+  Then use --tunnet=bridge:lg0 when launching the guest.
+
+  See http://linux-net.osdl.org/index.php/Bridge for general information
+  on how to get bridging working.
+
+- You can also create an inter-guest network using
+  "--sharenet=<filename>": any two guests using the same file are on
+  the same network.  This file is created if it does not exist.
+
+Lguest I/O model:
+
+Lguest uses a simplified DMA model plus shared memory for I/O.  Guests
+can communicate with each other if they share underlying memory
+(usually by the lguest program mmaping the same file), but they can
+use any non-shared memory to communicate with the lguest process.
+
+Guests can register DMA buffers at any key (must be a valid physical
+address) using the LHCALL_BIND_DMA(key, dmabufs, num<<8|irq)
+hypercall.  "dmabufs" is the physical address of an array of "num"
+"struct lguest_dma": each contains a used_len, and an array of
+physical addresses and lengths.  When a transfer occurs, the
+"used_len" field of one of the buffers which has used_len 0 will be
+set to the length transferred and the irq will fire.
+
+Using an irq value of 0 unbinds the dma buffers.
+
+To send DMA, the LHCALL_SEND_DMA(key, dma_physaddr) hypercall is used,
+and the bytes used is written to the used_len field.  This can be 0 if
+noone else has bound a DMA buffer to that key or some other error.
+DMA buffers bound by the same guest are ignored.
+
+Cheers!
+Rusty Russell rusty@rustcorp.com.au.
+
+[1] These are on various places on the TODO list, waiting for you to
+    get annoyed enough at the limitation to fix it.
+[2] Lguest is not yet tickless when idle.  See [1].